A data-driven signal processing method and system based on improved flower pollination

Abstract

This invention discloses a data-driven signal processing method and system based on improved flower pollination. The method includes: constructing an input-output model based on a target single-input single-output discrete-time nonlinear system; generating an iterative input model based on the input-output model and a projection algorithm; obtaining target parameters of the iterative input model; iterating the target parameters based on the improved flower pollination algorithm, wherein multiple update schemes are used to optimize the local and global pollination processes in the flower pollination algorithm to obtain the improved flower pollination algorithm; when the number of iterations reaches the maximum number of iterations, updating the target parameters based on the last iteration; and generating a data-driven signal processing model based on model-free adaptive control based on the updated target parameters and the iterative input model. This invention can optimize the parameters of the data-driven signal processing model based on model-free adaptive control, exhibiting good performance.

Description

Technical Field

[0001] This invention relates to the field of parameter optimization, and in particular to a data-driven signal processing method and system based on improved flower pollination. Background Technology

[0002] Currently, data-driven signal processing methods, whether for single-input single-output discrete-time nonlinear systems or multi-input multi-output discrete-time nonlinear systems, largely rely on experience, extensive experimental tuning, or random selection of fixed values ​​for setting system parameters. This introduces a degree of randomness, and the extensive experimental tuning or manual adjustment requires considerable manpower and time, making it time-consuming, labor-intensive, and unintelligent. Since these parameters often change depending on the control system or desired output, the randomness in parameter setting of data-driven signal processing systems based on model-free adaptive control (MFAC) leads to poor system tracking performance, thus affecting the overall system performance.

[0003] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0004] The main objective of this invention is to provide a data-driven signal processing method, system, terminal, and computer-readable storage medium based on improved flower pollination. This invention aims to solve the problem in the prior art where the randomness of parameter settings in data-driven signal processing systems based on model-free adaptive control leads to poor system tracking performance, thereby affecting the corresponding system performance, due to the randomness of parameter settings when facing different control systems or desired outputs.

[0005] To achieve the above objectives, the present invention provides a data-driven signal processing method based on improved flower pollination, the method comprising the following steps:

[0006] Based on the target single-input single-output discrete-time nonlinear system, an input-output model is constructed, and an iterative input model is generated based on the input-output model and the projection algorithm.

[0007] The target parameters of the iterative input model are obtained, and the target parameters are iterated based on the improved flower pollination algorithm. In this process, multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm.

[0008] When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the last iteration. Based on the updated target parameters and the iterative input model, a data-driven signal processing model based on model-free adaptive control is generated.

[0009] Optionally, the step of constructing an input-output model based on the target single-input single-output discrete-time nonlinear system, and generating an iterative input model based on the input-output model and the projection algorithm, specifically includes:

[0010] Obtain the target single-input single-output discrete-time nonlinear system, and construct an input-output model based on the target single-input single-output discrete-time nonlinear system;

[0011] Based on the theorem satisfied by the target single-input single-output discrete-time nonlinear system, the input-output model is transformed into an equivalent dynamic linearized data model.

[0012] According to the projection algorithm, a criterion function for pseudo-partial derivatives in the equivalent dynamic linearized data model is generated. The optimal conditions are solved according to the criterion function. The pseudo-partial derivative formula is generated according to the optimal conditions and the criterion function.

[0013] Obtain the desired system output, and generate the iterative input model based on the desired system output and the pseudo-partial derivative formula.

[0014] Optionally, obtaining the desired system output and generating the iterative input model based on the desired system output and the pseudo-partial derivative formula specifically includes:

[0015] Obtain the desired system output, and generate a criterion function based on the desired system output;

[0016] The equivalent dynamic linearized data model is updated according to the pseudo-partial derivative formula to obtain the updated equivalent dynamic linearized data model. The updated equivalent dynamic linearized data model is then substituted into the criterion function, and the partial derivative with respect to the input is calculated to obtain the current optimal condition.

[0017] The iterative input model is generated based on the current optimal conditions and the pseudo-partial derivative formula.

[0018] Optionally, obtaining the target parameters of the iterative input model and iterating the target parameters based on the improved flower pollination algorithm specifically includes:

[0019] Obtain the target parameters of the iterative input model, initialize the population size based on the target parameters, and initialize the switching probability, maximum number of iterations, and dimension of individuals in the population;

[0020] In each iteration, it is determined whether the current iteration number is within the maximum iteration number. If the current iteration number is within the maximum iteration number, a random number is generated, and it is determined whether the random number is greater than the switching probability. If it is greater, the global pollination process is used to calculate the next iteration solution of the current solution of each individual. If it is not greater, the local pollination process is used to calculate the next iteration solution of the current solution of each individual. The objective function value of the next iteration solution of the current solution of each individual is calculated, and the global optimal solution is updated based on all objective function values.

[0021] Optionally, the step of calculating the next iteration solution for the current solution of each individual using the global pollination process specifically includes:

[0022] The next iteration solution for each individual's current solution is calculated using a global pollination process, whereby the global pollination process is expressed as the following formula:

[0023]

[0024] Among them, x i,g+1 Let x represent the next iteration solution of the i-th solution. i,g Let ξ represent the current position of the i-th solution, ξ be the scaling factor of the guiding step size, i be a positive integer in the set {1,2,...,N}, r be a random number generated within [0,1], and t be the current iteration number. max The maximum number of iterations is given, where L represents the pollination intensity, and gbest is the maximum number of iterations. g It is the current optimal solution, x r1,g and x r2,g These are two solutions randomly selected from the population when the number of iterations is t. v is a random number generated by uniform distribution in the interval [0,1], and r1 and r2 are numbers randomly generated between 0 and 1.

[0025] Optionally, the step of calculating the next iteration solution for the current solution of each individual using the local pollination process specifically includes:

[0026] The iterative solution for the next time step of the current solution for each individual is calculated using a local pollination process, which is expressed by the following formula:

[0027]

[0028] Among them, x m1,g x m2,g x m3,g x m4,g These are different solutions randomly selected from the population when the number of iterations is t, where ζ, ζ1, and ζ2 are step size scaling factors.

[0029] Optionally, when the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the last iteration, and a data-driven signal processing model based on model-free adaptive control is generated based on the updated target parameters and the iterative input model, specifically including:

[0030] When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the global optimal solution obtained in the last iteration.

[0031] The updated target parameters are used to replace the corresponding parameters in the iterative input model to generate a data-driven signal processing model based on model-free adaptive control.

[0032] Furthermore, to achieve the above objectives, the present invention also provides a data-driven signal processing system based on improved flower pollination, wherein the data-driven signal processing system based on improved flower pollination includes:

[0033] The model generation module is used to construct an input-output model based on the target single-input single-output discrete-time nonlinear system, and to generate an iterative input model based on the input-output model and the projection algorithm.

[0034] An iteration module is used to obtain the target parameters of the iterative input model and iterate the target parameters based on the improved flower pollination algorithm. In this module, multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm.

[0035] The result generation module is used to obtain updated target parameters based on the last iteration when the number of iterations reaches the maximum number of iterations, and to generate a data-driven signal processing model based on model-free adaptive control based on the updated target parameters and the iterative input model.

[0036] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a data-driven signal processing program based on improved flower pollination stored in the memory and executable on the processor, wherein when the data-driven signal processing program based on improved flower pollination is executed by the processor, it implements the steps of the data-driven signal processing method based on improved flower pollination as described above.

[0037] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a data-driven signal processing program based on improved flower pollination, and when the data-driven signal processing program based on improved flower pollination is executed by a processor, it implements the steps of the data-driven signal processing method based on improved flower pollination as described above.

[0038] In this invention, an input-output model is constructed based on the target single-input single-output discrete-time nonlinear system. An iterative input model is generated based on the input-output model and a projection algorithm. The target parameters of the iterative input model are obtained, and the target parameters are iteratively applied based on an improved flower pollination algorithm. Multiple update schemes are used to optimize the local and global pollination processes in the flower pollination algorithm, resulting in the improved flower pollination algorithm. When the maximum number of iterations is reached, the target parameters are updated based on the last iteration. A data-driven signal processing model based on model-free adaptive control is generated based on the updated target parameters and the iterative input model. This invention improves upon the flower pollination algorithm (FPA) to propose an improved flower pollination algorithm with global optimization capabilities. Applying this improved flower pollination algorithm to the parameter optimization of the data-driven signal processing model based on model-free adaptive control avoids the problem of system performance being affected by the application of incorrect parameters due to random parameters, thereby further ensuring that the performance of the data-driven signal processing model based on model-free adaptive control remains at a good level. Attached Figure Description

[0039] Figure 1 This is a flowchart of a preferred embodiment of the present invention based on an improved data-driven signal processing method for flower pollination;

[0040] Figure 2 This is a schematic diagram of the system control input during the simulation process of an embodiment of the data-driven signal processing method for improved flower pollination according to the present invention;

[0041] Figure 3 This is a schematic diagram of the system pseudo-partial derivatives of an embodiment of the data-driven signal processing method for improved flower pollination based on the present invention.

[0042] Figure 4 This is a schematic diagram of the system output tracking performance during the simulation process of an embodiment of the data-driven signal processing method for improved flower pollination based on the present invention.

[0043] Figure 5 This invention relates to the SISO system output y, which addresses undesirable parameters in the improved data-driven signal processing method for flower pollination. * Tracking performance diagram;

[0044] Figure 6 This is a schematic diagram of the algorithm flow in the data-driven signal processing method for improved flower pollination based on the present invention;

[0045] Figure 7 This is a flowchart illustrating a preferred embodiment of the data-driven signal processing method for improved flower pollination according to the present invention.

[0046] Figure 8 This is a schematic diagram illustrating the output tracking performance of the MFAC-based data-driven signal processing system based on random selection of participants in the data-driven signal processing method for improved flower pollination in this invention.

[0047] Figure 9 This is a schematic diagram comparing the convergence performance of the proposed MFAC data-driven signal processing SISO system parameters after optimization by the MFAC data-driven signal processing system and three classic natural heuristic algorithms in the improved flower pollination data-driven signal processing method of this invention.

[0048] Figure 10 This is a structural diagram of a preferred embodiment of the data-driven signal processing system for improved flower pollination based on the present invention;

[0049] Figure 11 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0051] Currently, data-driven signal processing methods, whether for single-input single-output discrete-time nonlinear systems or multi-input multi-output discrete-time nonlinear systems, largely rely on experience, extensive experimental tuning, or random selection of fixed values ​​for system parameter settings. This introduces a degree of randomness, and the extensive experimental tuning or manual adjustments require considerable manpower and time, making them time-consuming, labor-intensive, and unintelligent. Since these parameters often change depending on the control system or desired output, the randomness in parameter settings of data-driven signal processing systems based on model-free adaptive control significantly impacts system tracking performance, failing to meet system expectations and resulting in ineffective performance guarantees.

[0052] To address one or more of the above-mentioned problems, this application constructs an input-output model based on the target single-input single-output discrete-time nonlinear system, generates an iterative input model based on the input-output model and a projection algorithm, obtains the target parameters of the iterative input model, iterates the target parameters based on an improved flower pollination algorithm, wherein multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm; when the number of iterations reaches the maximum number of iterations, the target parameters are updated based on the last iteration, and a data-driven signal processing model based on model-free adaptive control is generated based on the updated target parameters and the iterative input model.

[0053] The preferred embodiment of the data-driven signal processing method based on improved flower pollination described in this invention, such as... Figure 1 As shown, the data-driven signal processing method based on improved flower pollination includes the following steps:

[0054] Step S10: Based on the target single-input single-output discrete-time nonlinear system, construct an input-output model, and generate an iterative input model based on the input-output model and the projection algorithm.

[0055] Specifically, in this application, for the target Single-Input Single-Output (SISO) discrete-time nonlinear system and the data-driven signal processing discrete-time SISO nonlinear system based on MFAC, the corresponding input-output model is constructed, and an iterative input model is constructed based on the corresponding input-output model.

[0056] Furthermore, the step of constructing an input-output model based on the target single-input single-output discrete-time nonlinear system, and generating an iterative input model based on the input-output model and the projection algorithm, specifically includes:

[0057] Obtain the target single-input single-output discrete-time nonlinear system, and construct an input-output model based on the target single-input single-output discrete-time nonlinear system;

[0058] Based on the theorem satisfied by the target single-input single-output discrete-time nonlinear system, the input-output model is transformed into an equivalent dynamic linearized data model.

[0059] According to the projection algorithm, a criterion function for pseudo-partial derivatives in the equivalent dynamic linearized data model is generated. The optimal conditions are solved according to the criterion function. The pseudo-partial derivative formula is generated according to the optimal conditions and the criterion function.

[0060] Obtain the desired system output, and generate the iterative input model based on the desired system output and the pseudo-partial derivative formula.

[0061] Specifically, a target single-input single-output discrete-time nonlinear system is obtained, and an input-output model is constructed based on the target single-input single-output discrete-time nonlinear system. The iterative input model is specifically shown in formula (1):

[0062] y(k)=f(y(k-1),...,y(kn p ),u(k),...,u(kn s (1)

[0063] Here, f(.) is an unknown nonlinear function. y(k) and u(k) are the output and input of the system at time k, respectively, and n... p and n s It is an unknown order.

[0064] The iterative input model, i.e., the dynamic linearization representation, is based on the following two assumptions; where, assumption 1: the function f(.) responds to input signals u(k),...,u(kn)... s The partial derivatives of (1) are continuous; Assumption 2: The nonlinear system (1) satisfies the generalized Lipschitz condition, that is, the Lipschitz continuity condition, which is the following formula (2):

[0065] |y(k)-y(k-1)|≤b|u(k)-u(k-1)|; (2)

[0066] For any k, the following premise holds:

[0067] Δu(k)=u(k)-u(k-1), Δu(k)≠0; (3)

[0068] Where b is a positive constant.

[0069] For any time k, the iterative input model (1) satisfies both assumptions 1 and 2. There must exist a pseudo-partial-derived (PPD) parameter that allows the input-output model to be converted into the following equivalent dynamic linearized data model, i.e., the following formula (4):

[0070]

[0071] in, It is the pseudo-partial derivative at the k-th measurement, and

[0072] Since the pseudo-partial derivative in formula (4) is unknown and there is a time delay, neither the traditional projection algorithm nor the least squares algorithm can track it well. An improved projection algorithm is used to estimate PPD and obtain the criterion function of the pseudo-partial derivative, which is specifically defined as follows: formula (5):

[0073]

[0074] Where μ > 0 is a weighting factor. for The estimated value. The decision function in formula (5) is calculated. The partial derivatives are then used to solve for the optimal conditions, which are expressed as the following formula (6):

[0075]

[0076] Combining equations (5) and (6), that is, combining the optimal condition and the criterion function, a pseudo-partial derivative formula can be generated, specifically as shown in equation (7):

[0077]

[0078] Where η is a constant step size greater than 0. To accurately track the pseudo-partial derivatives that change with iteration and to ensure that formula (4) always holds true, this application also employs the following reset scheme:

[0079] if

[0080] Or |Δu(k)|≤σ or

[0081]

[0082] in, Let σ be the initial value of PPD, and let σ be a small positive constant.

[0083] Furthermore, the step of obtaining the desired system output and generating the iterative input model based on the desired system output and the pseudo-partial derivative formula specifically includes:

[0084] Obtain the desired system output, and generate a criterion function based on the desired system output;

[0085] The equivalent dynamic linearized data model is updated according to the pseudo-partial derivative formula to obtain the updated equivalent dynamic linearized data model. The updated equivalent dynamic linearized data model is then substituted into the criterion function, and the partial derivative with respect to the input is calculated to obtain the current optimal condition.

[0086] The iterative input model is generated based on the current optimal conditions and the pseudo-partial derivative formula.

[0087] Specifically, obtain the given desired system output y. * When we need to find the corresponding input u(k), we need to consider the following criterion function for the input u(k):

[0088] J(u(k))=|y *(k)-y(k)|+λ|u(k)-u(k-1)| 2 (9)

[0089] Where λ is a weighting factor. Therefore, the equivalent dynamic linearized data model is updated according to the pseudo-partial derivative formula, that is, by combining equation (7), (4) is rewritten as follows to update the equivalent dynamic linearized data model:

[0090]

[0091] Substitute the updated equivalent dynamic linearized data model into the criterion function and take the partial derivative with respect to the input, that is, substitute formula (10) into formula (9), take the partial derivative with respect to u(k) in formula (9), and solve for the optimal condition to obtain the current optimal condition, which is the following formula (11):

[0092]

[0093] Furthermore, based on the current optimal conditions and the pseudo-partial derivative formula, the iterative input of the control system is generated, i.e., the iterative input model:

[0094]

[0095] Where ρ is the step size constant.

[0096] Step S20: Obtain the target parameters of the iterative input model, and iterate the target parameters based on the improved flower pollination algorithm. In this step, multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm.

[0097] Specifically, the iterative input model includes four parameters: λ, ρ, μ, and η. This application optimizes the selection of the initial values ​​of these four parameters for the SISO system, a data-driven signal processing algorithm based on MFAC. In one embodiment, the initial conditions for system input and output are set as follows: u(1) = 0, u(2) = 0.5, y(1) = y(2) = 1; the corresponding parameter settings are shown in Table 1 below:

[0098] Table 1. Initial values ​​of parameters

[0099] parameter λ η ρ μ Numerical 1.2 2.5 3.2 1.6

[0100] For Table 1, a corresponding target single-input single-output discrete-time nonlinear system is selected as the MFAC-based data-driven signal processing system. The corresponding target single-input single-output discrete-time nonlinear system is shown in the following formula (13):

[0101]

[0102] Where b(k) is a time-varying parameter, its expression is shown in the following formula (14):

[0103] b(k)=0.1+0.1round(k / 100); (14)

[0104] The round function is used to round to the nearest integer.

[0105] Consider a type of step signal as the system tracking output for simulation. In this case, the desired signal y... * Set the following formula (15):

[0106]

[0107] The simulation results for the step signal are as follows: Figure 2 , Figure 3 and Figure 4 As shown. Among them, Figure 2 This is a schematic diagram of the system control inputs during the simulation process. Figure 3 This is a schematic diagram of the pseudo-partial derivatives of the system. Figure 4 This is a schematic diagram illustrating the system's output tracking performance. From... Figure 4 The comparison between the system iterative control output and the expected output shows that the system control output has a large overshoot near the step transition of the step signal, and the tracking performance is relatively average, but the overall tracking performance error is within a relatively small range.

[0108] Taking the signal in formula (15) as an example, a set of different parameters is selected to demonstrate the performance differences. Among them, a set of parameter values ​​different from those in Table 1 are selected to demonstrate the impact of randomly selected parameters on the algorithm performance.

[0109] Random initial values ​​of each parameter in Table 2 and Formula 15

[0110] parameter λ η ρ μ value 0.8 4.8 4.7 2.4

[0111] Based on the parameters in Table 2, the target single-input single-output discrete-time nonlinear system control output tracking performance is as follows: Figure 5 As shown. Figure 5 The system output tracking effect shown and Figure 4 The difference is very obvious; as iterations continue, Figure 5 The control output in the algorithm experienced increasing overshoot in subsequent iterations, and the final iteration did not accurately track the expected output. Therefore, randomly selecting parameters may have significantly impacted the algorithm's tracking performance, making it difficult for the control output to perform well.

[0112] because Figure 4The results in formulas (7) and (12) rely on experience to select the values ​​of parameters λ, ρ, μ, and η, but the optimal unknown parameters λ, ρ, μ, and η are not fixed. The selection of the values ​​of unknown parameters λ, ρ, μ, and η will affect the corresponding tracking performance. Figure 5 As shown, the uncertainty of unknown parameters can adversely affect the design of control systems. Although parameter values ​​can be selected through manual experiments, this approach is often arbitrary and increases labor costs in practical data-driven signal processing. To improve the system performance of MFAC-based data-driven signal processing technology, this application utilizes an improved flower pollination algorithm to optimize data parameters.

[0113] Furthermore, obtaining the target parameters of the iterative input model and iterating the target parameters based on the improved flower pollination algorithm specifically includes:

[0114] Obtain the target parameters of the iterative input model, initialize the population size based on the target parameters, and initialize the switching probability, maximum number of iterations, and dimension of individuals in the population;

[0115] In each iteration, it is determined whether the current iteration number is within the maximum iteration number. If the current iteration number is within the maximum iteration number, a random number is generated, and it is determined whether the random number is greater than the switching probability. If it is greater, the global pollination process is used to calculate the next iteration solution of the current solution of each individual. If it is not greater, the local pollination process is used to calculate the next iteration solution of the current solution of each individual. The objective function value of the next iteration solution of the current solution of each individual is calculated, and the global optimal solution is updated based on all objective function values.

[0116] Specifically, the Flower Pollination Algorithm (FPA) process includes cross-pollination and self-pollination. Correspondingly, cross-pollination can be defined as global pollination, used to explore a region of the search space to find the optimal region; abiotic self-pollination can be described as utilizing the region surrounding the current solution to accelerate convergence to a locally optimal solution; flower constancy can be viewed as a reproduction ratio proportional to the similarity between two flowers; compared to global pollination, local pollination has a slight advantage due to physical and external natural factors. Specifically, local and global pollination are controlled by a control variable p with a value between 0 and 1.

[0117] Correspondingly, the mathematical model steps for global pollination and flower constancy can be expressed as the following formula (16):

[0118] x i,g+1 =x i,g +ξL(gbest g -x i,g(16)

[0119] Where g represents the current iteration, x i,g It is the current position of the i-th solution, x i,g+1 Let ξ represent the iterative solution at the next time step of the i-th solution, and its dimension is determined by the number of variables in the problem; ξ is the scaling factor for the guiding step size. g The best solution is i, where i is a positive integer in the set {1,2,...,N}, and L is the pollination intensity, which is generated according to the Levy distribution with a β exponent, as shown in the following formula (17):

[0120]

[0121] Where Γ(β) represents the standard gamma distribution.

[0122] The mathematical model for local pollination is shown in the following formula (18):

[0123] x i,g+1 =x i,g +ζ(x m1,g -x m2,g (18)

[0124] Where m1 and m2 are different integers selected from the set {1,2,...,N}, x m1,g and x m2,g Two solutions are randomly selected from the current solution population, while ζ is a variable that is uniformly and randomly selected from [0,1].

[0125] Pollination behavior is performed globally and locally with a certain switching probability. Using the switching probability p as the switching probability for random selection, the entire FPA can be expressed as the following formula (19):

[0126]

[0127] Where r is a random number generated in the range [0,1].

[0128] FPA (Flower Pollination Algorithm) has the advantages of being easy to implement, having high optimization efficiency, and being robust. However, it also suffers from a weakening optimization performance in the later stages of algorithm iteration and difficulty in escaping local optima. To address this drawback of FPA getting trapped in local optima, this application further optimizes it to improve its global search capability, thus avoiding being trapped in local minima and achieving better optimization results. This paper proposes a novel Modified Flower Pollination Algorithm (MFPA), which establishes an effective mathematical model based on the efficient mixing of various update schemes, enabling the proposed MFPA to be more comprehensive in finding solutions to global optimization problems.

[0129] Specifically, in the improved flower pollination algorithm, the global pollination and local pollination around FPA are optimized by modifying formulas (16) and (18).

[0130] Furthermore, the step of calculating the next iteration solution for the current solution of each individual using the global pollination process specifically includes:

[0131] The next iteration solution for each individual's current solution is calculated using a global pollination process, whereby the global pollination process is expressed as the following formula:

[0132]

[0133] Among them, x i,g+ 1 represents the next iteration solution of the i-th solution, x i,g Let ξ represent the current position of the i-th solution, ξ be the scaling factor of the guiding step size, i be a positive integer in the set {1,2,...,N}, r be a random number generated within [0,1], and t be the current iteration number. max The maximum number of iterations is given, where L represents the pollination intensity, and gbest is the maximum number of iterations. g It is the current optimal solution, x r1,g and x r2,g These are two solutions randomly selected from the population when the number of iterations is t. v is a random number generated by uniform distribution in the interval [0,1], and r1 and r2 are numbers randomly generated between 0 and 1.

[0134] Specifically, in this application, for global pollination in flower pollination algorithms, the classic FPA (Fluidized Approach to Pollination) designs a mathematical model for global pollination, which is based on the process of different insects spreading pollen between different plants; and based on the reverse update of the current position to the best solution so far, gbest. gThe goal of this stage is to spread pollen over greater distances. Since the primary objective is to disperse pollen to distant areas for pollination of other plants, it's unnecessary to always move the current position in the opposite direction to the best position so far. Therefore, this application considers increasing population diversity among individuals by using multiple update schemes to bring pollen to more diverse regions, allowing it to explore more pollination scenarios within the search space and thus avoiding getting trapped in local optima, which could significantly impact the optimization process. During optimization, the improved flower pollination algorithm effectively switches between three different update schemes for global pollination, enabling pollen to reach multiple regions during the optimization process.

[0135] The improved flower pollination algorithm includes three update schemes. The first update scheme associates the current position with each search agent in the current iteration to help the algorithm gradually explore the regions around the current solution in the search space until the termination condition of the iteration is reached. In this case, the optimization process will focus on local search around the current solution in order to find a better solution. The specific first update scheme is shown in the following formula (20):

[0136]

[0137] Where g represents the current iteration, x i,g It is the current position of the i-th solution, x i,g+1 This represents the iterative solution at the next time step after the i-th solution, and its dimension is determined by the number of variables in the problem. max The maximum number of iterations is given by t, the current iteration number is given by , L is a distance control factor used to determine the distance around the current location to be detected, also called pollination intensity, and ξ is a scaling factor for the guide step size. g It is the best solution to date.

[0138] The second update scheme is based on a two-step search around the current best solution; the first step reverses the search for the optimal solution of the algorithm, while the second update scheme aims to improve this direction and bring it closer to the best solution so far, thereby further enhancing the algorithm's exploration capability. The specific second update scheme is shown in the following formula (21):

[0139]

[0140] Among them, x r1,g and x r2,g The two solutions are randomly selected from the population when the number of iterations is t, while r is a random number generated in the interval [0,1] under a uniform distribution.

[0141] The third update scheme is based on uniform distribution, exploring the region between the current optimal solution position and its opposite position to avoid getting trapped in local optima. The specific third update scheme is shown in formula (22) below:

[0142] x i,g+1 =gbest g .v; (22)

[0143] Where v is a random number generated by a uniform distribution in the interval [0,1], as shown in formula (23):

[0144] v = U(0,1); (23)

[0145] The specific form of switching between these three update schemes, namely the global pollination process, is shown in the following formula (24), in order to balance the implementation of one update scheme with the implementation of the other two update schemes, and thus attempt to balance exploration capability and optimization capability:

[0146]

[0147] r, r1, and r2 are numbers randomly generated between 0 and 1.

[0148] Furthermore, the step of calculating the next iteration solution for the current solution of each individual using the local pollination process specifically includes:

[0149] The iterative solution for the next time step of the current solution for each individual is calculated using a local pollination process, which is expressed by the following formula:

[0150]

[0151] Among them, x m1,g x m2,g x m3,g x m4,g These are different solutions randomly selected from the population when the number of iterations is t, where ζ, ζ1, and ζ2 are step size scaling factors.

[0152] Specifically, regarding the modification of the mathematical model for the local pollination process, this application designs it based on two different steps and uses a switching probability of 0.5 to achieve a balance between them. The first step is to perform a scaling search around the current position according to the current iteration amount to improve the searchability of the algorithm in the search space and avoid getting trapped in a local minimum. Specifically, equation (18) is modified to obtain the following formula (25):

[0153]

[0154] The second step involves searching for the best solution so far and expanding upon it based on the current iteration to improve the efficiency of finding the optimal solution, accelerate the convergence speed, and guide it in the right direction towards the optimal solution. The specific formula is shown below:

[0155]

[0156] Combining the two equations, we obtain the local pollination process. The local pollination process of the improved flower pollination algorithm is expressed as shown in the following formula (27):

[0157]

[0158] Among them, x m1,g x m2,g x m3,g x m4,g These are different solutions randomly selected from the population when the number of iterations is t, where ζ, ζ1, and ζ2 are step size scaling factors, and r is a random number in [0,1].

[0159] Correspondingly, after obtaining the improved flower pollination algorithm, the target parameters of the iterative input model are obtained, and the target parameters are iterated based on the improved flower pollination algorithm.

[0160] Specifically, in implementation, such as Figure 6 and Figure 7 As shown, first initialize: N, P, t max D; where N is the population size, p is the switching probability, and g is the population size. max Here, g is the maximum number of iterations, and D is the dimension of the individuals in the population. During algorithm execution, the above data is initialized first, followed by the initialization of the population x. Then, it is determined whether the current iteration count is less than the maximum iteration count, i.e., g < gmax. max When the conditions are met, a random number r is created between 0 and 1. If r > p, the next iteration solution of the current solution of each individual is calculated through the global pollination process, i.e., formula (24). If the conditions are not greater than p, the next iteration solution of the current solution of each individual is calculated through the local pollination process, i.e., formula (27). Then the objective function value of the next iteration solution of the current solution of each individual is calculated, and the global optimal solution is updated according to all objective function values. The objective parameters of the iterative input model are λ, ρ, μ, and η, but are not limited to these four. Other parameters can also be optimized. These parameters are used as the corresponding population. The number of individuals in the population, the switching probability, the maximum number of iterations, and the dimension of individuals in the population can be set by themselves. The corresponding switching probability is preferably set to 0.5, and the dimension of individuals in the population is set to the number of parameters that need to be further optimized, i.e., 4.

[0161] In the process of iterating the target parameters based on the improved flower pollination algorithm, each time the global optimal solution is updated, the corresponding iterative input model is updated using formulas (1) to (12) through the corresponding parameters, and then its performance is judged to select the corresponding global optimal solution.

[0162] Step S30: When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the last iteration. Based on the updated target parameters and the iterative input model, a data-driven signal processing model based on model-free adaptive control is generated.

[0163] Specifically, in this application, when the number of iterations reaches the maximum number of iterations, the optimized target parameters can be obtained, and the corresponding model can be generated by updating the target parameters.

[0164] Furthermore, when the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the last iteration. Based on the updated target parameters and the iterative input model, a data-driven signal processing model based on model-free adaptive control is generated, specifically including:

[0165] When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the global optimal solution obtained in the last iteration.

[0166] The updated target parameters are used to replace the corresponding parameters in the iterative input model to generate a data-driven signal processing model based on model-free adaptive control.

[0167] Specifically, in this application, when the number of iterations reaches the maximum number of iterations, the global optimal solution obtained in the last iteration is used as the output of the corresponding improved flower pollination algorithm. The updated target parameters, i.e. the updated values ​​of parameters λ, ρ, μ, and η, can be obtained through this output. The updated target parameters are used to replace the corresponding parameters in the original iterative input model, and the resulting model is the optimized data-driven signal processing model based on model-free adaptive control.

[0168] Furthermore, this application compares the optimization capabilities of the proposed MFPA with those of PSO, FPA, and GSA for parameters of MFAC-based data-driven signal processing systems. In this application, each variable dimension in the population set of MFPA, PSO, FPA, and GSA is set to the number of parameters requiring further optimization; that is, the population individual dimension is four times the number of optimization parameters in the MFAC data-driven signal processing SISO system. The maximum number of iterations for optimizing the MFAC data-driven signal processing algorithms based on MFPA, PSO, FPA, and GSA is set to 30. To reduce error, each algorithm undergoes 30 independent repeated trials, and the average of the 30 iterations is compared. Other specific parameter values ​​are as follows: the initial values ​​of λ, ρ, μ, and η are random numbers randomly selected from the interval [0,5]; the population size of the three heuristic algorithms PSO, FPA, and GSA is N = 50; in the PSO algorithm, the inertia weight is set to δ = 0.8, the cognitive rate c1 = 2, and the social rate c2 = 2; in FPA, the switching probability is set to p = 0.25, the step size scaling factor ξ = 0.8, while ζ and r are uniformly randomly selected from the interval [0,1] in each iteration, and the Levy distribution index β = 1.5; in GSA, the gravity constant is... The initial values ​​of the gravity constant are G0 = 150 and the attenuation rate is α = 20; the MFPA switching probability is set to p = 0.25, the step size scaling factor is ξ = 0.8, and v, ζ, ζ1, ζ2, r, r1 and r2 are randomly generated between 0 and 1 in each iteration.

[0169] To compare the parameter optimization capabilities of the proposed MFPA with PSO, FPA, and GSA for MFAC-based data-driven signal processing systems, this invention optimizes the parameters of an MFAC-based data-driven signal processing SISO system.

[0170] This invention selects the system in formula (13) for simulation experiments, and simultaneously sets the desired output y * (k) is set as follows: (28)

[0171] y * (k) = 0.5 + 0.5 × (-1) round(k / 200) (28)

[0172] The round function is used to round to the nearest integer.

[0173] The performance of the MFAC-based data-driven signal processing algorithm optimized by MFPA is compared with that of the algorithm with randomly selected parameters. The iterative output signal tracking performance under different parameters is as follows: Figure 8 As shown. From Figure 8It can be seen that the iterative control output of the system obtained by the MFAC data-driven signal processing algorithm with optimized parameters using MFPA exhibits smaller overshoot and better tracking performance, with the system control output gradually converging as the number of iterations increases. In contrast, the controller output of the MFAC data-driven signal processing algorithm designed based on randomly selected parameters shows significant overshoot, severe jitter, and poor tracking performance, with a performance significantly different from the iterative control output obtained by the MFPA-optimized MFAC data-driven signal processing algorithm. This indicates that the MFPA proposed in this invention can optimize the parameters of the MFAC-based data-driven signal processing system, thereby improving the tracking performance of the control system. Therefore, the MFAC data-driven signal processing system with parameter optimization based on the MFPA algorithm has better system stability and robustness than the MFAC data-driven signal processing system with randomly selected parameters.

[0174] To demonstrate the difference between the output of the improved flower pollination algorithm and the desired output, this invention sets the optimization objective as minimizing the error between the iterative control output and the desired output. The designed function expression is as follows (29):

[0175]

[0176] Where y(k) is the iterative control output, K is the maximum iteration time, and the optimization objective is to minimize the value of f. This application uses the reciprocal of the minimum objective function value f as a reference benchmark, and then normalizes and forward-directs the iterative objective function f value. Correspondingly, the experimental results of parameter optimization performance of the MFAC data-driven signal processing SISO system optimized based on the proposed MFPA, PSO, FPA, and GSA are as follows: Figure 9 As shown.

[0177] from Figure 9 It can be seen that in the early stages of iteration, the GSA algorithm did not perform well in the parameter optimization of the MFAC-based data-driven signal processing SISO system. It stalled after nearly eight iterations, getting stuck in a local optimum, and its parameter optimization performance was the worst among the four algorithms. The proposed MFPA algorithm, however, consistently achieved a convergence rate above 0.8 for parameter optimization of the MFAC-based data-driven signal processing SISO system. With increasing iterations, the optimization performance of the proposed MFPA algorithm was gradually improved. Furthermore, the proposed MFPA algorithm showed a significant performance improvement compared to the FPA and PSO algorithms. Figure 8This invention demonstrates that the proposed optimization method can help the classic FPA algorithm achieve performance levels that it cannot reach, thus exhibiting superior global optimization capabilities. Compared to the classic PSO, FPA, and GSA, the MFPA proposed in this invention offers better overall performance in optimizing the parameters of the MFAC data-driven signal processing SISO system, and can better guarantee the system's tracking performance.

[0178] Table 3. Simulation results of the objective function of the SISO system optimized based on the MFPA algorithm.

[0179]

[0180] Table 3 shows the maximum (worst), average, and minimum (best) values ​​of the objective function f obtained by different algorithms in 30 independent runs when optimizing the parameters of the MFAC-based data-driven signal processing SISO system using the proposed algorithm and three traditional natural heuristic algorithms. As can be seen from Table 3, the proposed MFPA algorithm has a significant performance advantage in optimizing the parameters of the MFAC-based data-driven signal processing SISO system. The PSO algorithm has the second best global parameter optimization performance, while the FPA and GSA algorithms have relatively poor global parameter optimization performance.

[0181] This invention constructs an input-output model for a target single-input single-output discrete-time nonlinear system. Based on this model and a projection algorithm, an iterative input model is generated. The target parameters of the iterative input model are obtained, and the target parameters are iteratively applied using an improved flower pollination algorithm. Multiple update schemes are employed to optimize the local and global pollination processes in the flower pollination algorithm, resulting in the improved flower pollination algorithm. When the maximum number of iterations is reached, the target parameters are updated based on the last iteration. Using the updated target parameters and the iterative input model, a data-driven signal processing model based on model-free adaptive control is generated. This invention improves upon the flower pollination algorithm, proposing an improved flower pollination algorithm with global optimization capabilities. Applying this improved flower pollination algorithm to the parameter optimization of the data-driven signal processing model based on model-free adaptive control avoids the performance issues caused by random parameters when incorrect parameters are applied, thus maintaining the performance of the data-driven signal processing model based on model-free adaptive control at a relatively good level.

[0182] Furthermore, such as Figure 10 As shown, based on the above-described data-driven signal processing method for improved flower pollination, the present invention also provides a data-driven signal processing system for improved flower pollination, wherein the data-driven signal processing system for improved flower pollination includes:

[0183] The model generation module 91 is used to construct an input-output model based on the target single-input single-output discrete-time nonlinear system, and to generate an iterative input model based on the input-output model and the projection algorithm.

[0184] The iteration module 92 is used to obtain the target parameters of the iterative input model and iterate the target parameters based on the improved flower pollination algorithm. In this process, multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm.

[0185] The result generation module 93 is used to obtain the updated target parameters based on the last iteration when the number of iterations reaches the maximum number of iterations, and to generate a data-driven signal processing model based on model-free adaptive control based on the updated target parameters and the iterative input model.

[0186] Furthermore, such as Figure 11 As shown, based on the above-mentioned data-driven signal processing method and system for improved flower pollination, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 11 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0187] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a data-driven signal processing program 40 based on improved flower pollination, which can be executed by the processor 10 to implement the data-driven signal processing method based on improved flower pollination in this application.

[0188] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the data-driven signal processing method based on improved flower pollination.

[0189] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

[0190] In one embodiment, the steps of the above-described data-driven signal processing method based on improved flower pollination are implemented when the processor 10 executes the data-driven signal processing program 40 based on improved flower pollination in the memory 20.

[0191] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a data-driven signal processing program based on improved flower pollination, and the data-driven signal processing program based on improved flower pollination, when executed by a processor, implements the steps of the data-driven signal processing method based on improved flower pollination as described above.

[0192] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0193] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0194] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A data-driven signal processing method based on improved flower pollination, characterized in that, The data-driven signal processing method based on improved flower pollination includes: Based on the target single-input single-output discrete-time nonlinear system, an input-output model is constructed, and an iterative input model is generated based on the input-output model and the projection algorithm. The target parameters of the iterative input model are obtained, and the target parameters are iterated based on the improved flower pollination algorithm. In this process, multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm. When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the last iteration. Based on the updated target parameters and the iterative input model, a data-driven signal processing model based on model-free adaptive control is generated. The process of obtaining the target parameters of the iterative input model and iterating the target parameters based on the improved flower pollination algorithm specifically includes: Obtain the target parameters of the iterative input model, initialize the population size based on the target parameters, and initialize the switching probability, maximum number of iterations, and dimension of individuals in the population; In each iteration, it is determined whether the current iteration number is within the maximum iteration number. If the current iteration number is within the maximum iteration number, a random number is generated, and it is determined whether the random number is greater than the switching probability. If it is greater, the global pollination process is used to calculate the next iteration solution of the current solution of each individual. If it is not greater, the local pollination process is used to calculate the next iteration solution of the current solution of each individual. The objective function value of the next iteration solution of the current solution of each individual is calculated, and the global optimal solution is updated based on all objective function values. The calculation of the next iteration solution for the current solution of each individual using the global pollination process specifically includes: The next iteration solution for each individual's current solution is calculated using a global pollination process, whereby the global pollination process is expressed as the following formula: Among them, x i,g+1 Let x represent the next iteration solution of the i-th solution. i,g Let ξ represent the current position of the i-th solution, ξ be the scaling factor of the guiding step size, i be a positive integer in the set {1,2,...,N}, r be a random number generated within [0,1], and t be the current iteration number. max The maximum number of iterations is given, where L represents the pollination intensity, and gbest is the maximum number of iterations. g It is the current optimal solution, x r1,g and x r2,g These are two solutions randomly selected from the population when the number of iterations is t, where v is a random number generated in a uniform distribution in the interval [0,1], and r1 and r2 are numbers randomly generated between 0 and 1; To increase population diversity among individuals, multiple update schemes will be used to bring pollen to more different regions, allowing it to explore more pollination situations in the search space and thus avoid getting trapped in local optima, which may significantly affect the optimization process. During the optimization process, the global pollination in the improved flower pollination algorithm effectively switches between three different update schemes, enabling pollen to reach multiple regions during the optimization process. The calculation of the next iteration solution for each individual's current solution using a local pollination process specifically includes: The iterative solution for the next time step of the current solution for each individual is calculated using a local pollination process, which is expressed by the following formula: Among them, x m1,g x m2,g x m3,g x m4,g These are different solutions randomly selected from the population when the number of iterations is t, where ζ, ζ1, and ζ2 are step size scaling factors. The mathematical model of the local pollination process was modified based on two different steps and switched using a switching probability of 0.5 to achieve a balance between them.

2. The data-driven signal processing method based on improved flower pollination according to claim 1, characterized in that, The process of constructing an input-output model based on the target single-input single-output discrete-time nonlinear system, and generating an iterative input model based on the input-output model and the projection algorithm, specifically includes: Obtain the target single-input single-output discrete-time nonlinear system, and construct an input-output model based on the target single-input single-output discrete-time nonlinear system; Based on the theorem satisfied by the target single-input single-output discrete-time nonlinear system, the input-output model is transformed into an equivalent dynamic linearized data model. According to the projection algorithm, a criterion function for pseudo-partial derivatives in the equivalent dynamic linearized data model is generated. The optimal conditions are solved according to the criterion function. The pseudo-partial derivative formula is generated according to the optimal conditions and the criterion function. Obtain the desired system output, and generate the iterative input model based on the desired system output and the pseudo-partial derivative formula.

3. The data-driven signal processing method based on improved flower pollination according to claim 2, characterized in that, The step of obtaining the desired system output and generating the iterative input model based on the desired system output and the pseudo-partial derivative formula specifically includes: Obtain the desired system output, and generate a criterion function based on the desired system output; The equivalent dynamic linearized data model is updated according to the pseudo-partial derivative formula to obtain the updated equivalent dynamic linearized data model. The updated equivalent dynamic linearized data model is then substituted into the criterion function, and the partial derivative with respect to the input is calculated to obtain the current optimal condition. The iterative input model is generated based on the current optimal conditions and the pseudo-partial derivative formula.

4. The data-driven signal processing method based on improved flower pollination according to claim 1, characterized in that, When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the last iteration. Based on the updated target parameters and the iterative input model, a data-driven signal processing model based on model-free adaptive control is generated, specifically including: When the number of iterations reaches the maximum number of iterations, the updated target parameters are obtained based on the global optimal solution obtained in the last iteration. The updated target parameters are used to replace the corresponding parameters in the iterative input model to generate a data-driven signal processing model based on model-free adaptive control.

5. A data-driven signal processing system based on improved flower pollination, characterized in that, The data-driven signal processing system based on improved flower pollination includes: The model generation module is used to construct an input-output model based on the target single-input single-output discrete-time nonlinear system, and to generate an iterative input model based on the input-output model and the projection algorithm. An iteration module is used to obtain the target parameters of the iterative input model and iterate the target parameters based on the improved flower pollination algorithm. In this module, multiple update schemes are used to optimize the local pollination process and the global pollination process in the flower pollination algorithm to obtain the improved flower pollination algorithm. The result generation module is used to obtain the updated target parameters based on the last iteration when the number of iterations reaches the maximum number of iterations, and to generate a data-driven signal processing model based on model-free adaptive control based on the updated target parameters and the iterative input model. The process of obtaining the target parameters of the iterative input model and iterating the target parameters based on the improved flower pollination algorithm specifically includes: Obtain the target parameters of the iterative input model, initialize the population size based on the target parameters, and initialize the switching probability, maximum number of iterations, and dimension of individuals in the population; In each iteration, it is determined whether the current iteration number is within the maximum iteration number. If the current iteration number is within the maximum iteration number, a random number is generated, and it is determined whether the random number is greater than the switching probability. If it is greater, the global pollination process is used to calculate the next iteration solution of the current solution of each individual. If it is not greater, the local pollination process is used to calculate the next iteration solution of the current solution of each individual. The objective function value of the next iteration solution of the current solution of each individual is calculated, and the global optimal solution is updated based on all objective function values. The calculation of the next iteration solution for the current solution of each individual using the global pollination process specifically includes: The next iteration solution for each individual's current solution is calculated using a global pollination process, whereby the global pollination process is expressed as the following formula: Among them, x i,g+1 Let x represent the next iteration solution of the i-th solution. i,g Let ξ represent the current position of the i-th solution, ξ be the scaling factor of the guiding step size, i be a positive integer in the set {1,2,...,N}, r be a random number generated within [0,1], and t be the current iteration number. max The maximum number of iterations is given, where L represents the pollination intensity, and gbest is the maximum number of iterations. g It is the current optimal solution, x r1,g and x r2,g These are two solutions randomly selected from the population when the number of iterations is t, where v is a random number generated in a uniform distribution in the interval [0,1], and r1 and r2 are numbers randomly generated between 0 and 1; To increase population diversity among individuals, multiple update schemes will be used to bring pollen to more different regions, allowing it to explore more pollination situations in the search space and thus avoid getting trapped in local optima, which may significantly affect the optimization process. During the optimization process, the global pollination in the improved flower pollination algorithm effectively switches between three different update schemes, enabling pollen to reach multiple regions during the optimization process. The calculation of the next iteration solution for each individual's current solution using a local pollination process specifically includes: The iterative solution for the next time step of the current solution for each individual is calculated using a local pollination process, which is expressed by the following formula: Among them, x m1,g x m2,g x m3,g x m4,g These are different solutions randomly selected from the population when the number of iterations is t, where ζ, ζ1, and ζ2 are step size scaling factors. The mathematical model of the local pollination process was modified based on two different steps and switched using a switching probability of 0.5 to achieve a balance between them.

6. A terminal, characterized in that, The terminal includes: a memory, a processor, and a data-driven signal processing program based on improved flower pollination stored in the memory and executable on the processor. When the data-driven signal processing program based on improved flower pollination is executed by the processor, it implements the steps of the data-driven signal processing method based on improved flower pollination as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a data-driven signal processing program based on improved flower pollination, which, when executed by a processor, implements the steps of the data-driven signal processing method based on improved flower pollination as described in any one of claims 1-4.

Images